INDEX

Explanations

programming terminology and structures related to function definitions and data handling

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GetEnumerator

-0.60

SPATH

-0.57

 Numerade

-0.52

Autoritní

-0.52

 IFTT

-0.52

>{@

-0.51

#+#

-0.51

 intptr

-0.49

disposing

-0.49

BorderFactory

-0.49

POSITIVE LOGITS

 initComponents

0.52

mybatisplus

0.42

 éstos

0.41

penuhi

0.38

 wichtiger

0.36

 Gegenteil

0.36

 kepad

0.36

 invités

0.35

 gelişti

0.33

يكب

0.33

Activations Density 0.250%

programming terminology and structures related to function definitions and data handling

No Comments

No Known Activations